ui-uitk

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides expert-level assistance for Unity UI Toolkit, following official patterns for UXML, USS, and C#. It includes explicit safety constraints, such as the prohibition of external URLs in USS url() properties, which prevents remote asset exfiltration or loading from untrusted sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface due to its ability to read and modify project-level code files. However, this functionality is the primary intended purpose of the skill. The risks are mitigated by the inclusion of asset-loading constraints and the reliance on the Unity Editor's internal compilers and parsers to validate generated content.
  • Ingestion points: Local project files referenced via Read, Glob, and Grep tools.
  • Boundary markers: The skill uses standard markdown formatting for code output and generation.
  • Capability inventory: Write and Edit tools permit modification of UI assets and C# scripts within the local project scope.
  • Sanitization: Generated code is validated by the Unity Editor's internal console and parsers upon reimport.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:23 AM
Security Audit — agent-trust-hub — ui-uitk